mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-04-29 10:51:51 +00:00
154e0d75fc
* Merging mainline - WIP * Merging mainline - WIP AVX2 and CUDA appear to work. CUDA performance seems slightly (~1-2%) lower as it is so often the case with llama.cpp/ggml after some "improvements" have been made. * Merging mainline - fix Metal * Remove check --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
34 lines
1.2 KiB
Plaintext
34 lines
1.2 KiB
Plaintext
#include "common.cuh"
|
|
|
|
#define CUDA_GELU_BLOCK_SIZE 256
|
|
#define CUDA_SILU_BLOCK_SIZE 256
|
|
#define CUDA_TANH_BLOCK_SIZE 256
|
|
#define CUDA_RELU_BLOCK_SIZE 256
|
|
#define CUDA_SIGMOID_BLOCK_SIZE 256
|
|
#define CUDA_HARDSIGMOID_BLOCK_SIZE 256
|
|
#define CUDA_HARDSWISH_BLOCK_SIZE 256
|
|
#define CUDA_SQR_BLOCK_SIZE 256
|
|
#define CUDA_SQRT_BLOCK_SIZE 256
|
|
|
|
void ggml_cuda_op_gelu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_silu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_gelu_quick(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_tanh(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_relu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_sigmoid(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_hardsigmoid(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_hardswish(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_leaky_relu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_sqr(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_sqrt(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|